Hi Everyone, I would like to invite you to a free webinar I am hosting today. It's a comparison of the 4 models: ChatGPT, Claude, Gemini and Copilot. Today, January 15th, 19:00 CET / 1:00 PM EST https://www.linkedin.com/events/4mainaichatbotscompared7414659699100344321/ It would be great to see some of you there. There will be gifts :-)

Today I spent a few hours revisiting Claude Code and Obsidian. Back in November I worked with Claude Code almost daily for 1 hour and explored what it can do. Since then I have gone deep into many different topics like RAG , and one thing became very clear: learning is not the problem. Structure is. For me, that structure is Obsidian combined with Claude Code. My setup is simple but powerful. All my notes go into a folder called “raw”. Everything I learn in communities, through hands on my experiments, or from tips and feedback you share with me. . All my recent experiences from Obsidian, the email sorting experiments, and all your hints and ideas now end up in this system as well. Nothing gets lost anymore. Everything flows into my second Obsidian brain. Claude Code then processes these notes. It restructures them, adds tags, creates links, and connects new knowledge with existing notes. Topics start to relate to each other naturally. Over time, a real knowledge graph emerges. I attached all the markdown files for anyone who wants to rebuild this setup. The system is described in six phases, explaining what to do and which commands to run. One downside: everything is in German, but that should be easy to translate, take an LLM like ChatGPT, Claude or Gemini. Now a few questions for the more advanced users here: Do you have an automation running for something like this? Do you use a dashboard to manage or track your knowledge base? And does anyone have a vector database connected to their notes so they can chat with them? Curious to see how others handle this.

What happens when you dive one hour a day into RAG with absolute intensity? I’m about to find out. Starting today, I’m committing to a personal challenge:Every single day, I will spend at least one hour digging deep into Retrieval-Augmented Generation and I’ll share every step of my progress right here. Why?Because I want to grow. Deeply. Consistently. With purpose.And because RAG is becoming one of the most important building blocks of future AI systems. To make this challenge truly powerful, I need your support and I need everything this community has. 🔥 I genuinely need all of it: – your RAG automations – your RAG-enabled AI agents – your workflows– your best practices – your mistakes and lessons– your resources, tutorials, and websites – every piece of knowledge that exists here – every experience you’ve made To start this challenge in the right way, I need your help with a few key questions: 🔍 Which RAG automations have you already built? 🔍 What RAG-related information, examples, or materials already exist in this community? 🔍 What was absolutely essential for you to truly understand RAG? 🔍 Which websites, videos, or tutorials helped you the most? 🔍 Which RAG systems have you built — and would you be open to sharing them with me? I’m excited to dive deeper every single day and to build real RAG excellence together with all of you. Let’s go. Please put all informations in the comments, it will be helpful

Today I wanted to talk to the data that now lives inside my Graph RAG and my Supabase vector database. So I rebuilt the chat pipeline to really understand what is happening behind the scenes. And just like yesterday… this Graph RAG truly feels like a monster. What came out of it is something I honestly find fascinating. I built my own personal patent assistant. I can now chat with my stored patent data. The system understands the meaning of my questions and automatically searches across all tables for the right information. The agent then connects everything together into a clear answer and, thanks to memory, it does not forget the context of our conversation. So instead of digging through endless lists, I can simply ask and get exactly what I need. There is a reason why this pipeline has so many nodes. My AI agent needs two different tools for each of my three tables: metadata, claims and prior art. One set of tools helps the agent understand the question and find the right documents.The other set loads the full detailed text from the archive when needed. Because of this design, the agent always has the right “specialized tool” for each part of the database. It can jump quickly between titles, legal sections and technical comparisons to build the best answer. Honestly, it still feels crazy to see what becomes possible once you start experimenting and rebuilding these things yourself.Without trying it hands on, I would have never imagined ideas like this. And I love how clearly you can influence the quality of RAG once you understand the structure behind it.

Today I actually planned to work on something else and i started also to build. But there is one topic I simply cannot ignore anymore. Also the Knowledge I got, but Secure is in the pole position. If I want to build RAG systems that companies will actually trust, then the system must be secure. The data must stay protected.And ideally, nothing should leave the company environment. That brought me to one big question: How do we build RAG with an LLM that does not send data outside? Someone already commented and suggested hosting an LLM myself. And now I really want to understand this topic. So here are my questions. On which cloud oder service is this easiest to do? AWS, Google Cloud, Azure, elestio something else? Which LLM makes sense for self-hosting? How would I connect a self-hosted LLM to n8n?Is it via API? And then the bigger question: Are there already tutorials, videos or good guides for this? Has anyone seen step-by-step explanations? I am also curious whether the community plans to show something like this in the future. Because I am sure I am not the only one thinking about it. A RAG system should not only work well. It also needs to be safe, private and compliant with company expectations. I really want to understand this topic deep. So if you have experience, ideas or resources, I would love to hear them. I think a lot of people will be looking forward 😁